JP3194419B2 - Inspection method for wrong parts of engine external parts - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method for inspecting an external component attached to an engine for a missing item.

[0002]

2. Description of the Related Art At the time of automobile production, after assembling an engine,
It is necessary to inspect for missing parts whether or not the external parts, for example, soft parts such as harnesses or hoses, are mounted at predetermined regular positions. Therefore, in the case of an automatic machine, arrows (Wa) and (Wb) in the engine (1) shown in FIG.
The presence / absence check (instrument inspection) at a predetermined position shown in (Wc) is performed by a contact sensor. Alternatively, it may be visually checked manually.

[0003]

The problem to be solved by the conventional means for inspecting a missing part of an external engine component is that the length and the type of the component are different or the shape is different, or the mounting position is changed due to replacement of an operator, or the hose is not used. It is not possible to perform an erroneous product inspection for checking the appearance such as the routing shape of a kind. SUMMARY OF THE INVENTION It is an object of the present invention to provide a method for inspecting missing parts of an external part of an engine, such as hoses, as well as a method of inspecting an incorrect part to check the type, shape, appearance, and the like.

[0004]

According to the present invention, an external part of an engine is imaged from a predetermined direction, an image screen is divided into a plurality of small areas, and each of the small areas is subjected to grayscale image processing to measure a brightness distribution. The process and the amount of change in the brightness distribution between the small areas are detected, and the detected data is compared with the reference data, and the degree of coincidence of the change with the reference data for each of the small areas is calculated as the center of gravity.
To calculate the difference between the detection data and the reference data.
Or the difference is divided by the base data to
And a step of determining the missing parts of the external parts of the engine based on the determination over all the small areas.

[0005]

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS FIGS. 1A and 1B show an embodiment of a method for inspecting a missing part of an external part of an engine according to the present invention.
This will be described below with reference to (c) and FIGS. 2 (a) and 2 (b). First, FIG. 1A shows an apparatus configuration for implementing a method of inspecting an engine for external parts according to the present invention, wherein (2) is a CCD camera, (3) is an image processing apparatus, and (4) ) Is a personal computer for fuzzy inference. CC above
The D camera (2) takes an image of an external component (for example, a hose) of the engine (5) from a predetermined direction, for example, from above and side,
The imaging screens (F) and (G) are shown in FIGS.
Note that (F) shows an imaging screen when a good hose that can be selected as a reference image described later is attached, and (G) shows an imaging screen when a wrong hose is attached. In particular, in FIG.
e) is an incorrect product with an incorrect mounting position.

[0006] The image processing apparatus (3) is shown in FIGS.
As shown in (1), the imaging screen (F) (G) by the CCD camera (2) is divided vertically and horizontally into a plurality of small areas (F1) (F2)... (G1) (G2). Each of the small areas (F1) (F2)... (G1) (G2)... Is subjected to gray-scale image processing (gray search) to measure the spatial lightness distribution in each area. Then, since the brightness changes locally in the area depending on the presence or absence or shape of an external component such as a hose, the presence or absence of the component and the schematic shape of the component can be detected from the brightness distribution in the small area. Then, the variation (A1) of the brightness distribution between the small areas (F1) and (F2)... Or the variation (Y1) of the brightness distribution between the small areas (G1) and (G2). Detect every time. Therefore, when the non-defective imaging screen (F) is selected as the reference image, the change amount (A) of the brightness distribution between the above detection data and the reference data divided by each small area (F1) (F2).
1)... Are compared with each other and, for example, both are subtracted to calculate a difference (Q1 = Y1-A1) from the reference data.

The personal computer (4) has a built-in fuzzy inference element, and determines how much each change amount (Y1) conforms to the reference data (A1) for each of the small areas (G1) and (G2). Judge by fuzzy inference. For example, the amount of change (Y1) between each of the small areas (G1), (G2),... By fuzzy inference center of gravity calculation based on the difference (Q1) calculated by the image processing device (3).
Are matched with the reference data (A1) to determine the degree of coincidence (V1). And the degree of coincidence (V1) ...
Is determined over all the small areas (G1), (G2)... And the type, shape and appearance of the external parts of the engine (5) are inspected to determine whether or not an erroneous product has occurred.

Next, the operation of the present invention based on the above configuration will be described. First, an external component of the engine (5) is imaged by a CCD camera (2) from a predetermined direction (above and side), and as shown in FIG. 1C, an image screen (G) is imaged by an image processing device (3). Is divided into a plurality of small areas (G1). Therefore, the spatial lightness distribution in the area is measured for each of the small areas (G1). Next, when attention is paid to the small areas (G8) between the small areas, for example, the adjacent upper, lower, left, and right small areas (G3), (G13), (G
7) The change in the brightness distribution between (G9), that is, the small area (G
8) and the lightness distribution differences (Y83), (Y813), (Y87), and (Y89) between the small areas (G3), (G13), (G7), and (G9) therearound are detected. When the fuzzy inference is performed by the center-of-gravity calculation, the difference (Q83 = Y83-A8) between the detected data and the reference data (A83) (A813) (A87) (A89) of the non-defective product set in advance.
3) Calculate ... Alternatively, the difference may be divided by the reference data to calculate a percentage value of the difference and standardized. Then, the difference (Q83) ... is input to the register of the personal computer (4), fuzzy inference is performed, and the small area (G8) and (G
3) The degree of coincidence (V83) of each brightness distribution difference between (G13), (G7) and (G9) with reference data is determined. Further, a fuzzy judgment is performed over all the small areas (G1)..., A plurality of data are judged, and the presence or absence of external parts of the engine, the appearance shape, and the like are checked to check for a missing part. At this time,
When the external components are imaged from two or more directions and the number of determination conditions is increased, the inspection accuracy is further improved.

Thus, even if the shape and type of the external parts of the engine (5) are changed, the missing parts can be inspected correspondingly. Further, when the illumination conditions change due to a change in the amount of light in the surroundings, the brightness distribution itself changes, but the amount of change in the brightness distribution between the small regions does not change. Therefore, it is possible to accurately and stably inspect the external parts of the engine (5) for missing parts regardless of changes in lighting conditions. Further, the number of divisions of the small area (G1)... May be appropriately increased or decreased in consideration of the information processing time.

At this time, the algorithm in the fuzzy inference is such that if the difference between the brightness distribution change between the small areas and the reference data is small, the degree of coincidence becomes large and the captured image of the engine external component is set in advance. When the reference image approaches the reference image and the difference is large, the degree of coincidence decreases and the reference image deviates from the reference image. Therefore, the following fuzzy rules are created according to the above algorithm.

(I) IF Qn (n = 1...) = ZR (Zero), THEN
Vn (n = 1 ...) = PL (Positive Large) (II) IF Qn (n = 1 ...) = PS (Positive Small), THEN V
n (n = 1 ...) = PS (III) IF Qn (n = 1 ...) = PM (Positive Medium), THEN
Vn (n = 1...) = ZR As a membership function for executing the fuzzy rule, a triangular membership function (Ma) (Mb) is set as shown in FIG. The membership function (Ma) relates to the input part (% value), and the membership function (Mb) relates to the output part (degree of coincidence). Therefore, for example, assuming that Qn = 5% as input data, the matching degree is 0.5 in rule (I), 0.5 in rule (II), and 0 in other cases. Therefore, the output (coincidence) is calculated by the center of gravity
(Vn) is near 2, which is quite close to the reference image. The above calculation is performed for all the small areas for the brightness distribution,
Inspect the external parts of the engine (5) for missing parts.

In the fuzzy inference, in addition to the above-described determination based on the calculation of the center of gravity, there is a determination means based on a probability. For example, FIG.
As shown in (b), the change amount (Y
1) Membership function of fuzzy set of (Mc) (however, (ZRa) is reference data, (PSa) (NSa) is each fuzzy set of displacement), and judgment probability (Dn) is for each small area Set to. Therefore, the degree of conformity (Ra) (Rb) to the reference data and the displacement is detected from the change amount (Y1) of the brightness distribution between the small areas. And the fitness (Ra)
Are larger and the degree of conformity (Rb) is smaller, the reference data is closer to the reference data. Therefore, they are compared with the determination probability (Dn) to determine the degree of coincidence (V1) of the amounts of change (Y1). For example, Ra>
When Dn> Rb, the degree of coincidence (V1) is determined to be within the normal range, and the determination operation is performed for each small area. Therefore, for example, the number of normal determinations is determined as a criterion from all determination results over all the small areas as a determination criterion, and an erroneous missing part of an external component of the engine (5) is inspected.

According to the present invention, the imaging screen of the external component of the engine is divided into a plurality of small areas, and the brightness distribution is measured by performing grayscale image processing in each of the small areas. The degree of coincidence with the reference data of the quantity is calculated by the center of gravity calculation.
Calculate or calculate the difference between the detected data and the reference data
Divide the difference by the base data to calculate the percent difference
Inspection of incorrect parts of the external parts of the engine was determined by fuzzy inference to be standardized, so that not only missing parts but also incorrect parts could be inspected, and regardless of changes in lighting conditions such as disturbance light fluctuation, Accurate inspection is possible and the inspection is stable, and
Accuracy also improves.

[Brief description of the drawings]

FIG. 1A is an apparatus configuration diagram for executing a method for inspecting an externally attached engine for a missing part according to the present invention.
(B) is a front view of a good-quality imaging screen of the engine external parts according to the present invention. FIG. 4C is a front view of a screen for imaging an incorrect product of an external component of the engine according to the present invention.

FIG. 2A is a waveform diagram of each membership function of an input / output unit for performing fuzzy inference in a method of inspecting an externally attached engine for a missing part according to the present invention. FIG. 6B is a waveform diagram of another membership function for performing fuzzy inference of the method for inspecting a missing part of an external component of an engine according to the present invention.

FIG. 3 is a perspective view of an engine showing an example of a conventional engine external component.

[Explanation of symbols]

 2 CCD camera 3 Image processing device 4 PC for fuzzy inference 5 Engine F, G Imaging screen F1…, G1… Small area

──────────────────────────────────────────────────続 き Continued on the front page (58) Field surveyed (Int.Cl. ⁷ , DB name) G01V 8/10 G06T 7/00

Claims (1)

(57) [Claims] A step of imaging an external component of the engine from a predetermined direction to divide an imaging screen into a plurality of small areas, and performing a grayscale image processing in each of the small areas to measure a lightness distribution; The amount of change in the brightness distribution is detected, and the detected data is compared with the reference data, and the degree of coincidence of the amount of change with the reference data is calculated for each small area by calculating the center of gravity.
Calculate the difference from the data or use the difference
Deciding by fuzzy inference that divides and calculates the percentage value of the difference to standardize the difference, and inspects the missing parts of the external parts of the engine from the judgment over all the small areas. Inspection method for missing parts of engine external parts.